© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41012
    Prev
    Next
    INDEX
    Explanations

    you. So

    np_acts-logits-general · gemini-2.5-flash-lite

    call pickup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ⲗ
    0.49
    ോഗ
    0.48
    ্ি
    0.48
    كلم
    0.48
    까지
    0.48
    같은
    0.46
    бліоте
    0.46
    änglich
    0.46
    尴
    0.46
    😧
    0.46
    POSITIVE LOGITS
     (
    0.45
     surpassing
    0.43
     supre
    0.42
     cost
    0.41
     surpasses
    0.41
     rounds
    0.41
     parallelogram
    0.40
     جنوبی
    0.40
    eto
    0.40
     Perm
    0.40
    Activations Density 0.000%

    No Known Activations